Skip to content

feat: Add a metric ingestion time SM sanitization #15222

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 2 commits into from
Dec 4, 2024
Merged

feat: Add a metric ingestion time SM sanitization #15222

Show file tree
Hide file tree
Changes from 1 commit
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
91cabf9
Add a metric for when a tenant has structured metadata sanitized at
cstyan Dec 3, 2024
bcbe1b4
lint
cstyan Dec 3, 2024
File filter

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
Next Next commit
Add a metric for when a tenant has structured metadata sanitized at 
ingestion time.

Signed-off-by: Callum Styan <callumstyan@gmail.com>
  • Loading branch information
@cstyan
cstyan committed Dec 3, 2024
commit 91cabf94a5527bfad4048a1f2e7fa27b4086fe30
22 changes: 17 additions & 5 deletions pkg/distributor/distributor.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -167,10 +167,11 @@ type Distributor struct {
RequestParserWrapper push.RequestParserWrapper

// metrics
ingesterAppends *prometheus.CounterVec
ingesterAppendTimeouts *prometheus.CounterVec
replicationFactor prometheus.Gauge
streamShardCount prometheus.Counter
ingesterAppends *prometheus.CounterVec
ingesterAppendTimeouts *prometheus.CounterVec
replicationFactor prometheus.Gauge
streamShardCount prometheus.Counter
tenantPushSanitizedStructuredMetadata *prometheus.CounterVec

usageTracker push.UsageTracker
ingesterTasks chan pushIngesterTask
Expand Down Expand Up @@ -284,6 +285,11 @@ func New(
Name: "stream_sharding_count",
Help: "Total number of times the distributor has sharded streams",
}),
tenantPushSanitizedStructuredMetadata: promauto.With(registerer).NewCounterVec(prometheus.CounterOpts{
Namespace: constants.Loki,
Name: "distributor_push_structured_metadata_sanitized_total",
Help: "The total number of times we've had to sanitize structured metadata (names or values) at ingestion time per tenant.",
}, []string{"tenant"}),
kafkaAppends: promauto.With(registerer).NewCounterVec(prometheus.CounterOpts{
Namespace: constants.Loki,
Name: "distributor_kafka_appends_total",
Expand Down Expand Up @@ -527,11 +533,17 @@ func (d *Distributor) Push(ctx context.Context, req *logproto.PushRequest) (*log
continue
}

var normalized string
structuredMetadata := logproto.FromLabelAdaptersToLabels(entry.StructuredMetadata)
for i := range entry.StructuredMetadata {
structuredMetadata[i].Name = otlptranslate.NormalizeLabel(structuredMetadata[i].Name)
normalized = otlptranslate.NormalizeLabel(structuredMetadata[i].Name)
if normalized != structuredMetadata[i].Name {
structuredMetadata[i].Name = normalized
d.tenantPushSanitizedStructuredMetadata.WithLabelValues(tenantID).Inc()
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

should we also add this for value sanitisation?
Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

yep, this just got missed in my git add --patch and then I saw the test failing as you posted your comment, pushed the value inc() call
}
if strings.ContainsRune(structuredMetadata[i].Value, utf8.RuneError) {
structuredMetadata[i].Value = strings.Map(removeInvalidUtf, structuredMetadata[i].Value)
d.tenantPushSanitizedStructuredMetadata.WithLabelValues(tenantID).Inc()
}
}
if shouldDiscoverLevels {
Expand Down
7 changes: 7 additions & 0 deletions pkg/distributor/distributor_test.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -3,6 +3,7 @@ package distributor
import (
"context"
"fmt"
"github.com/prometheus/client_golang/prometheus/testutil"
"math"
"math/rand"
"net/http"
Expand Down Expand Up @@ -1961,22 +1962,27 @@ func TestDistributor_StructuredMetadataSanitization(t *testing.T) {
for _, tc := range []struct {
req *logproto.PushRequest
expectedResponse *logproto.PushResponse
numSanitizations float64
}{
{
makeWriteRequestWithLabels(10, 10, []string{`{foo="bar"}`}, true, false, false),
success,
0,
},
{
makeWriteRequestWithLabels(10, 10, []string{`{foo="bar"}`}, true, true, false),
success,
10,
},
{
makeWriteRequestWithLabels(10, 10, []string{`{foo="bar"}`}, true, false, true),
success,
10,
},
{
makeWriteRequestWithLabels(10, 10, []string{`{foo="bar"}`}, true, true, true),
success,
20,
},
} {
distributors, _ := prepare(t, 1, 5, limits, nil)
Expand All @@ -1988,5 +1994,6 @@ func TestDistributor_StructuredMetadataSanitization(t *testing.T) {
response, err := distributors[0].Push(ctx, &request)
require.NoError(t, err)
assert.Equal(t, tc.expectedResponse, response)
assert.Equal(t, tc.numSanitizations, testutil.ToFloat64(distributors[0].tenantPushSanitizedStructuredMetadata.WithLabelValues("test")))
}
}
Loading